© 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. 5154
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    1343
    +0.14
    0.4%
    1108
    +0.11
    0.3%
    776
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1988
    +0.14
    0.03
    49
    +0.11
    0.03
    1108
    +0.10
    0.03
    Negative Logits
     ve
    -0.61
    adaptiveStyles
    -0.59
     so
    -0.58
     from
    -0.58
     “
    -0.56
     из
    -0.56
     тук
    -0.56
     at
    -0.55
    .”
    -0.55
     in
    -0.54
    POSITIVE LOGITS
     cabrio
    1.53
     clio
    1.50
     murano
    1.49
     peugeot
    1.47
     immen
    1.42
     lamborghini
    1.40
     vespa
    1.40
     pessi
    1.38
     gsx
    1.37
     michelin
    1.37
    Activations Density 0.026%

    No Known Activations