© 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. 14569
    Prev
    Next
    INDEX
    Explanations

    words related to specific names and locations

    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
    1984
    +0.10
    0.3%
    776
    +0.09
    0.3%
    874
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.10
    0.03
    113
    +0.09
    0.02
    227
    +0.07
    0.04
    Negative Logits
     Administrativna
    -0.75
    -------------</
    -0.72
    Waar
    -0.61
    Vidu
    -0.61
    Referencoj
    -0.60
    Característica
    -0.60
    Causas
    -0.60
    Eksteraj
    -0.60
    Læs
    -0.59
     beginnetje
    -0.59
    POSITIVE LOGITS
     intersper
    1.32
     unspeak
    1.26
     inconce
    1.23
     shenan
    1.20
     accla
    1.20
     disagre
    1.19
     reluct
    1.19
    '
    1.15
     apprehen
    1.15
     encomp
    1.14
    Activations Density 0.189%

    No Known Activations