© 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. 14133
    Prev
    Next
    INDEX
    Explanations

    mentions of specific place names and political events

    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
    1553
    +0.08
    0.2%
    615
    +0.07
    0.2%
    776
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1014
    +0.08
    0.03
    198
    +0.07
    0.03
    493
    +0.07
    0.03
    Negative Logits
    ividual
    -0.59
    seks
    -0.57
     jaya
    -0.56
     interessa
    -0.56
     tait
    -0.54
     troviamo
    -0.53
     mahd
    -0.53
     jawa
    -0.53
     alip
    -0.52
    thage
    -0.52
    POSITIVE LOGITS
    ValueGeneration
    0.59
    calciatore
    0.53
    unref
    0.53
    kleine
    0.53
     whereof
    0.50
     collectivités
    0.49
     davon
    0.49
     requiring
    0.49
    μφωνα
    0.48
    JAKARTA
    0.48
    Activations Density 0.151%

    No Known Activations