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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13021
    Prev
    Next
    INDEX
    Explanations

    ISBN numbers and publication information

    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
    1343
    +0.13
    0.4%
    1403
    +0.11
    0.3%
    1235
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1597
    +0.13
    0.03
    1105
    +0.11
    0.04
    1343
    +0.10
    0.04
    Negative Logits
     
    -0.79
     (
    -0.79
    ,
    -0.78
     he
    -0.76
     at
    -0.76
     de
    -0.76
     in
    -0.75
     a
    -0.75
     earnestness
    -0.74
    .
    -0.74
    POSITIVE LOGITS
     kram
    2.41
     utop
    2.23
     glan
    2.18
     gmbh
    2.16
     alkoh
    2.14
     meis
    2.04
     plak
    2.03
     aquare
    2.02
     siff
    2.00
     elek
    2.00
    Activations Density 0.165%

    No Known Activations