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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12646
    Prev
    Next
    INDEX
    Explanations

    phrases related to application or submission

    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
    32
    +0.16
    0.6%
    1325
    +0.13
    0.5%
    390
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    32
    +0.16
    0.03
    1325
    +0.13
    0.02
    1778
    +0.12
    0.02
    Negative Logits
    htë
    -0.57
    usermodel
    -0.49
    木坂
    -0.49
    getMinutes
    -0.48
     Meg
    -0.45
    GRAFIA
    -0.44
    ceis
    -0.44
     للاسماء
    -0.43
    Meg
    -0.42
     Mes
    -0.42
    POSITIVE LOGITS
     applied
    1.13
     apply
    1.13
     Apply
    1.10
    applied
    1.10
     Applied
    1.09
    Applied
    1.09
    APPLY
    1.08
     Applies
    1.08
    apply
    1.07
    Apply
    1.06
    Activations Density 0.063%

    No Known Activations