© 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. 13924
    Prev
    Next
    INDEX
    Explanations

    phrases with negative connotations or controversial topics

    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
    201
    +0.15
    0.7%
    680
    +0.12
    0.5%
    629
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    201
    +0.15
    0.02
    1174
    +0.12
    0.02
    981
    +0.12
    0.03
    Negative Logits
    Iglesia
    -0.50
     święta
    -0.43
     Sánchez
    -0.43
     Williams
    -0.42
     száll
    -0.42
    classnames
    -0.41
     RELIGION
    -0.41
     Петра
    -0.40
     Rivers
    -0.40
     vertelt
    -0.40
    POSITIVE LOGITS
     Fo
    1.18
    Fo
    1.14
     FO
    1.05
    fo
    0.97
     fo
    0.97
    FO
    0.87
     Foil
    0.87
     foams
    0.84
     FOG
    0.83
     foaming
    0.82
    Activations Density 0.138%

    No Known Activations