© 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. 3398
    Prev
    Next
    INDEX
    Explanations

    information related to location and technical details like configurations, servers, and hardware components

    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
    1150
    +0.19
    0.5%
    2034
    +0.12
    0.3%
    227
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1150
    +0.19
    0.02
    1471
    +0.12
    0.03
    1392
    +0.09
    0.03
    Negative Logits
    sizePolicy
    -0.65
     solidar
    -0.62
     febr
    -0.61
    المشاركات
    -0.58
    Pautan
    -0.58
     psychiat
    -0.57
     melat
    -0.56
     prostitu
    -0.56
    Elaboración
    -0.56
    المناصب
    -0.55
    POSITIVE LOGITS
     indestru
    0.97
     pamph
    0.94
     shenan
    0.94
     reluct
    0.94
     sophistic
    0.92
     philanth
    0.92
     intersper
    0.91
     unspeak
    0.89
     apprehen
    0.89
     encomp
    0.88
    Activations Density 0.107%

    No Known Activations