© 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. 7637
    Prev
    Next
    INDEX
    Explanations

    controversial topics and arguments

    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
    674
    +0.11
    0.3%
    510
    +0.07
    0.2%
    604
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1677
    +0.11
    0.03
    1269
    +0.07
    0.03
    1395
    +0.07
    0.03
    Negative Logits
     fta
    -2.05
     increa
    -1.92
     emphat
    -1.91
     fte
    -1.87
     ftu
    -1.84
     inev
    -1.81
     squa
    -1.80
     aton
    -1.78
     Juf
    -1.76
     disagre
    -1.75
    POSITIVE LOGITS
     also
    0.86
     shouldn
    0.75
     should
    0.73
     também
    0.72
    also
    0.70
     cannot
    0.67
     ALSO
    0.66
     Also
    0.66
     does
    0.66
     también
    0.66
    Activations Density 0.214%

    No Known Activations