© 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. 902
    Prev
    Next
    INDEX
    Explanations

    mentions of legal and political issues

    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
    2019
    +0.12
    0.4%
    304
    +0.11
    0.3%
    752
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    950
    +0.12
    0.03
    1003
    +0.11
    0.02
    932
    +0.10
    0.02
    Negative Logits
     xPos
    -0.89
     startX
    -0.86
     swarovski
    -0.81
     OnTrigger
    -0.73
     tupperware
    -0.71
     posX
    -0.70
     sherds
    -0.70
     sculptured
    -0.70
     unspeak
    -0.68
     hairc
    -0.68
    POSITIVE LOGITS
     minimalis
    0.83
     compil
    0.81
     utop
    0.81
     solidar
    0.80
     ordina
    0.78
     incess
    0.78
     suscit
    0.78
     alkoh
    0.78
     logis
    0.77
     gymnas
    0.76
    Activations Density 0.066%

    No Known Activations