© 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. 13765
    Prev
    Next
    INDEX
    Explanations

    quotations and names

    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
    889
    +0.12
    0.4%
    1145
    +0.11
    0.4%
    1741
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    889
    +0.12
    0.02
    1127
    +0.11
    0.02
    1141
    +0.10
    0.02
    Negative Logits
     türlü
    -0.50
     Brüder
    -0.49
    putable
    -0.49
    ideration
    -0.48
    upply
    -0.47
    avía
    -0.47
    leggings
    -0.47
    pullover
    -0.46
    ufficient
    -0.46
     bezeichneter
    -0.46
    POSITIVE LOGITS
     Ms
    1.08
    Ms
    1.04
     ms
    0.89
     noyau
    0.83
     Cfr
    0.82
     convenable
    0.80
     MS
    0.78
     Ams
    0.76
     renforcé
    0.73
     rafra
    0.72
    Activations Density 0.027%

    No Known Activations