© 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. 13089
    Prev
    Next
    INDEX
    Explanations

    words related to programming languages and coding activities

    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
    1403
    +0.10
    0.3%
    1531
    +0.10
    0.3%
    1553
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1553
    +0.10
    0.04
    235
    +0.10
    0.03
    1415
    +0.08
    0.02
    Negative Logits
     increa
    -1.79
     Juf
    -1.77
     inev
    -1.74
     thut
    -1.72
     fta
    -1.70
     emphat
    -1.68
     dises
    -1.67
     effe
    -1.67
     volunte
    -1.66
     secon
    -1.63
    POSITIVE LOGITS
    <bos>
    1.00
     choosing
    0.73
     buying
    0.71
     choose
    0.71
     yourself
    0.69
     purchasing
    0.68
     purchase
    0.67
    选择
    0.66
    选
    0.66
     selecting
    0.65
    Activations Density 0.320%

    No Known Activations