© 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. 13737
    Prev
    Next
    INDEX
    Explanations

    political discussions and perspectives

    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
    1577
    +0.11
    0.4%
    2034
    +0.11
    0.3%
    814
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.11
    0.03
    814
    +0.11
    0.02
    699
    +0.10
    0.03
    Negative Logits
     occupe
    -0.64
    Consig
    -0.64
    Lma
    -0.61
     estime
    -0.59
    Buona
    -0.59
     reconnaît
    -0.59
     ouvre
    -0.59
     assiste
    -0.58
     recru
    -0.55
     déclare
    -0.55
    POSITIVE LOGITS
     AppColors
    0.73
     jaya
    0.66
     SUDOC
    0.64
     tsi
    0.63
     umo
    0.61
     siena
    0.61
    actéristique
    0.61
    actéris
    0.60
     strto
    0.59
     saba
    0.59
    Activations Density 0.115%

    No Known Activations