© 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. 7534
    Prev
    Next
    INDEX
    Explanations

    references to news articles about various incidents

    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
    2019
    +0.22
    0.7%
    381
    +0.15
    0.5%
    331
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    331
    +0.22
    0.04
    950
    +0.15
    0.04
    924
    +0.11
    0.04
    Negative Logits
     himo
    -0.69
    Kde
    -0.66
    Flere
    -0.59
    Tja
    -0.58
    Üdv
    -0.58
     OnTrigger
    -0.57
    roleum
    -0.54
    Köszönöm
    -0.53
    Výhody
    -0.53
     OnEnable
    -0.52
    POSITIVE LOGITS
    .-(
    0.77
     renfer
    0.62
    Dilution
    0.62
     encomp
    0.61
    Sched
    0.61
    .-"
    0.61
    Semantics
    0.60
    Lengths
    0.59
    Periods
    0.59
    $(-
    0.58
    Activations Density 0.089%

    No Known Activations