© 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. 3407
    Prev
    Next
    INDEX
    Explanations

    mentions of software systems and technologies within a business context

    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
    678
    +0.24
    0.8%
    876
    +0.19
    0.6%
    283
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.24
    0.11
    283
    +0.19
    0.02
    1177
    +0.14
    0.04
    Negative Logits
    <bos>
    -1.76
     그의
    -0.82
     at
    -0.81
     in
    -0.78
     no
    -0.77
     once
    -0.76
     about
    -0.76
     during
    -0.75
     may
    -0.75
     to
    -0.74
    POSITIVE LOGITS
     overla
    2.51
     wien
    2.34
     milano
    2.33
     abnorm
    2.26
     mef
    2.24
     erec
    2.24
     effe
    2.23
     franz
    2.22
     immen
    2.21
     gmbh
    2.21
    Activations Density 0.527%

    No Known Activations