© 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. 2314
    Prev
    Next
    INDEX
    Explanations

    names of characters, particularly those related to espionage or criminal investigations

    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
    1343
    +0.10
    0.3%
    792
    +0.10
    0.3%
    304
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.10
    0.02
    792
    +0.10
    0.03
    788
    +0.09
    0.03
    Negative Logits
     bituminous
    -0.65
     vorliegenden
    -0.63
     CRITERIA
    -0.62
     SAMPLING
    -0.61
     aeration
    -0.59
     apertures
    -0.58
     nozzles
    -0.58
     einheit
    -0.57
     insulators
    -0.57
     flocc
    -0.56
    POSITIVE LOGITS
     Sén
    1.28
     Châ
    1.24
     Meilleur
    1.18
     embra
    1.17
     paillettes
    1.15
     Mâ
    1.12
     Moderato
    1.12
     suspic
    1.11
     Méri
    1.10
     Aprile
    1.09
    Activations Density 0.235%

    No Known Activations