© 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. 14516
    Prev
    Next
    INDEX
    Explanations

    phrases related to abstract concepts or hypothetical situations

    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
    1324
    +0.09
    0.3%
    109
    +0.08
    0.2%
    381
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.09
    0.03
    1919
    +0.08
    0.05
    1324
    +0.07
    0.05
    Negative Logits
    vantages
    -0.59
     frito
    -0.57
     lele
    -0.56
    quante
    -0.55
    gese
    -0.54
     noël
    -0.54
     vété
    -0.54
     papà
    -0.53
     parlamento
    -0.53
    rure
    -0.52
    POSITIVE LOGITS
     procedere
    0.59
    ValueStyle
    0.59
     addirittura
    0.54
     notare
    0.53
     purtroppo
    0.53
     disreg
    0.52
    zbęd
    0.52
    SneakyThrows
    0.52
    VYMaps
    0.50
     vorrei
    0.50
    Activations Density 0.689%

    No Known Activations