© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 6094
    Prev
    Next
    INDEX
    Explanations

    instructions or advice related to throwing objects accurately, with a focus on technique and precision

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    874
    +0.13
    0.4%
    1145
    +0.11
    0.4%
    1562
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    874
    +0.13
    0.04
    1935
    +0.11
    0.03
    1155
    +0.10
    0.03
    Negative Logits
    WarningLevel
    -0.54
    Điện
    -0.53
    DataColumn
    -0.52
    DatabaseError
    -0.51
    DataPropertyName
    -0.50
    scalatest
    -0.49
     sê
    -0.49
    HasMaxLength
    -0.48
    ModelMap
    -0.48
    CreateIndex
    -0.48
    POSITIVE LOGITS
     throw
    1.19
     Throwing
    1.14
     thrown
    1.13
     throwing
    1.11
     threw
    1.08
    throwing
    1.05
    Throwing
    1.04
     Throw
    1.04
     throws
    1.02
     Throws
    0.99
    Activations Density 0.123%

    No Known Activations