© 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. 13841
    Prev
    Next
    INDEX
    Explanations

    words related to technology or computer programming, specifically focusing on object-oriented programming concepts

    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
    507
    +0.12
    0.4%
    1343
    +0.11
    0.3%
    1967
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    507
    +0.12
    0.04
    523
    +0.11
    0.03
    956
    +0.10
    0.03
    Negative Logits
     vainly
    -0.71
     unspeak
    -0.63
     unavoid
    -0.60
     testifies
    -0.56
     OBSERVATIONS
    -0.55
     supposes
    -0.55
     unbear
    -0.54
     indescri
    -0.54
     disambiguazione
    -0.53
     frowns
    -0.53
    POSITIVE LOGITS
     sappi
    0.91
     venuto
    0.79
     riuscito
    0.74
     vogli
    0.71
     parlando
    0.70
     Ottobre
    0.68
     arrivato
    0.67
    bbene
    0.67
     persino
    0.67
     voleva
    0.67
    Activations Density 0.244%

    No Known Activations