© 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. 3454
    Prev
    Next
    INDEX
    Explanations

    information related to historical events or geographical locations

    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
    1978
    +0.13
    0.5%
    1334
    +0.13
    0.5%
    1865
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.13
    0.07
    321
    +0.13
    0.07
    1065
    +0.12
    0.06
    Negative Logits
     guerrillas
    -0.47
     peasantry
    -0.46
     reciprocity
    -0.45
     Soviets
    -0.44
    GEBURTSDATUM
    -0.43
     مرئيه
    -0.43
    írez
    -0.43
     armis
    -0.42
    Tikang
    -0.42
     tyrants
    -0.42
    POSITIVE LOGITS
     gmbh
    0.73
     tene
    0.71
     meis
    0.71
     paff
    0.68
     Konkur
    0.66
     fatis
    0.66
     maniere
    0.63
     ACKNOWLEDGMENTS
    0.62
     zoll
    0.61
     karton
    0.61
    Activations Density 0.233%

    No Known Activations