© 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 EvalsExportsAPI 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. 13221
    Prev
    Next
    INDEX
    Explanations

    descriptive details and actions related to a narrative

    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
    1233
    +0.10
    0.3%
    486
    +0.10
    0.3%
    1351
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    254
    +0.10
    0.02
    1032
    +0.10
    0.02
    1619
    +0.10
    0.02
    Negative Logits
    Πηγές
    -0.66
    foque
    -0.65
    Τι
    -0.65
    İstinadlar
    -0.64
    Sqft
    -0.64
     ModelExpression
    -0.63
    Filmo
    -0.62
     kanton
    -0.62
    ftagPool
    -0.61
     Walkover
    -0.61
    POSITIVE LOGITS
     reluct
    1.54
     encomp
    1.49
     disagre
    1.49
     maneu
    1.48
     increa
    1.42
     guarante
    1.42
     inev
    1.40
     shenan
    1.38
     volunte
    1.37
     intersper
    1.36
    Activations Density 0.047%

    No Known Activations