© 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. 12875
    Prev
    Next
    INDEX
    Explanations

    phrases related to 'vs' or 'versus'

    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
    1187
    +0.14
    0.5%
    605
    +0.10
    0.3%
    1233
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1187
    +0.14
    0.02
    499
    +0.10
    0.02
    1604
    +0.10
    0.02
    Negative Logits
     prek
    -0.68
     moze
    -0.68
     zima
    -0.57
     vne
    -0.56
     jeste
    -0.55
     kona
    -0.55
     vode
    -0.54
    !«
    -0.54
     preva
    -0.54
     zama
    -0.54
    POSITIVE LOGITS
     vs
    0.99
    vs
    0.91
     Vs
    0.83
     VS
    0.80
    VS
    0.76
     Versus
    0.74
    versus
    0.72
     versus
    0.71
     nephe
    0.69
    Versus
    0.66
    Activations Density 0.062%

    No Known Activations