© 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. 16250
    Prev
    Next
    INDEX
    Explanations

    names of athletes and sports terms, especially related to American football and gaming

    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
    1177
    +0.14
    0.5%
    1265
    +0.13
    0.5%
    897
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    662
    +0.14
    0.06
    1177
    +0.13
    0.03
    405
    +0.12
    0.04
    Negative Logits
    <bos>
    -1.49
    Todavía
    -0.60
    pueden
    -0.56
     a
    -0.55
     im
    -0.55
    Esperamos
    -0.55
    Pued
    -0.54
     density
    -0.54
    algunos
    -0.53
     split
    -0.53
    POSITIVE LOGITS
     mef
    1.37
     lele
    1.35
     gmbh
    1.32
     hcm
    1.30
     michelin
    1.30
     beverly
    1.24
     tanga
    1.23
     lara
    1.23
     hina
    1.23
     bangkok
    1.23
    Activations Density 0.369%

    No Known Activations