© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 971
    Prev
    Next
    INDEX
    Explanations

    words related to politics and policies

    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
    394
    +0.11
    0.3%
    507
    +0.10
    0.3%
    1820
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    507
    +0.11
    0.06
    1820
    +0.10
    0.05
    1783
    +0.09
    0.06
    Negative Logits
     autunno
    -0.65
     affitto
    -0.61
    sune
    -0.61
     déjeuner
    -0.60
     salvador
    -0.57
     appartiennent
    -0.57
     noël
    -0.57
    ficult
    -0.57
    ragal
    -0.56
     poulet
    -0.56
    POSITIVE LOGITS
     alike
    0.93
     are
    0.92
     aren
    0.80
     were
    0.79
     weren
    0.78
     arent
    0.72
     have
    0.70
    
    
    0.70
     respectivamente
    0.65
     bave
    0.63
    Activations Density 0.595%

    No Known Activations