© 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. 3375
    Prev
    Next
    INDEX
    Explanations

    adjectives describing the novelty and uniqueness of something

    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
    1013
    +0.10
    0.3%
    642
    +0.08
    0.2%
    1910
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.10
    0.03
    319
    +0.08
    0.03
    792
    +0.08
    0.02
    Negative Logits
    Avez
    -0.57
     maging
    -0.54
     Redacción
    -0.51
    Aprend
    -0.50
     compréhen
    -0.49
    iglesia
    -0.49
    Imágenes
    -0.48
    Argumento
    -0.48
    Sábado
    -0.48
     ilang
    -0.48
    POSITIVE LOGITS
     stratigraph
    0.82
     outlander
    0.73
     kraken
    0.71
     snoopy
    0.70
     bordeaux
    0.69
     oleo
    0.66
     mariner
    0.66
     unve
    0.66
     friable
    0.65
     tupperware
    0.65
    Activations Density 0.167%

    No Known Activations