© 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. 13718
    Prev
    Next
    INDEX
    Explanations

    research-related terms and concepts

    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
    1241
    +0.08
    0.2%
    872
    +0.08
    0.2%
    1129
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    378
    +0.08
    0.04
    581
    +0.08
    0.05
    1241
    +0.07
    0.05
    Negative Logits
     Mlle
    -0.96
     encomp
    -0.94
     indestru
    -0.93
     fortn
    -0.93
     accla
    -0.88
     inconce
    -0.88
     increa
    -0.87
     unve
    -0.84
     philanth
    -0.83
     gardent
    -0.82
    POSITIVE LOGITS
    InjectAttribute
    0.62
    principalTable
    0.59
    KEYCODE
    0.58
     censiti
    0.56
    MessageOf
    0.56
     currently
    0.56
     really
    0.56
     adequately
    0.55
     nor
    0.55
     truly
    0.54
    Activations Density 0.489%

    No Known Activations