© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14925
    Prev
    Next
    INDEX
    Explanations

    complex or technical terms

    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
    597
    +0.16
    0.6%
    1896
    +0.11
    0.4%
    82
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    597
    +0.16
    0.03
    124
    +0.11
    0.02
    321
    +0.10
    0.03
    Negative Logits
    Siga
    -0.55
    Desen
    -0.52
    Filosof
    -0.49
    Significado
    -0.49
    Obra
    -0.48
    Quais
    -0.46
    História
    -0.45
    Nesta
    -0.45
    dataclass
    -0.45
    tslib
    -0.45
    POSITIVE LOGITS
     exp
    1.06
     EXP
    1.00
     Exp
    0.99
    exp
    0.94
    Exp
    0.92
    EXP
    0.88
     expon
    0.85
     xp
    0.83
     exponents
    0.81
     popoli
    0.81
    Activations Density 0.138%

    No Known Activations