© 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. 3797
    Prev
    Next
    INDEX
    Explanations

    timestamps and channel names related to sports programming

    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
    +0.17
    0.5%
    1445
    +0.12
    0.4%
    906
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.17
    0.04
    267
    +0.12
    0.03
    1803
    +0.12
    0.03
    Negative Logits
     gaily
    -0.65
     bronco
    -0.58
     głó
    -0.55
     apprehen
    -0.53
     aislada
    -0.52
     overcrow
    -0.52
     ornamented
    -0.51
     vainly
    -0.50
     cálido
    -0.50
     impatiently
    -0.49
    POSITIVE LOGITS
     Più
    1.00
     apparti
    1.00
     Così
    0.94
     Altri
    0.93
     Queste
    0.92
     Puoi
    0.92
     trasforma
    0.91
     succede
    0.90
     Abbiamo
    0.89
     sappi
    0.88
    Activations Density 0.123%

    No Known Activations