© 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. 13927
    Prev
    Next
    INDEX
    Explanations

    information related to criminal investigations and incidents

    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
    1539
    +0.12
    0.3%
    297
    +0.11
    0.3%
    198
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1539
    +0.12
    0.07
    946
    +0.11
    0.08
    736
    +0.10
    0.09
    Negative Logits
    SequentialGroup
    -0.54
     parteci
    -0.54
    <bos>
    -0.54
    bewerken
    -0.53
     parlano
    -0.53
     chi̍t
    -0.52
    guisement
    -0.51
    ItemLayout
    -0.51
    собенности
    -0.51
    Εκ
    -0.50
    POSITIVE LOGITS
     Juf
    1.07
     pamph
    1.03
     Thier
    1.01
     encomp
    1.00
     fta
    1.00
     apprehen
    0.99
     ftu
    0.98
     Daven
    0.98
     fup
    0.96
     Glou
    0.94
    Activations Density 1.703%

    No Known Activations