© 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. 7591
    Prev
    Next
    INDEX
    Explanations

    political scandals and controversies

    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
    1438
    +0.12
    0.4%
    1896
    +0.11
    0.4%
    1870
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1047
    +0.12
    0.02
    1531
    +0.11
    0.02
    1173
    +0.11
    0.02
    Negative Logits
    OGND
    -0.67
     vern
    -0.54
     aquare
    -0.54
     impon
    -0.54
     utop
    -0.54
    المكان
    -0.54
    ConstraintMaker
    -0.51
     artistico
    -0.51
    hartt
    -0.51
    पया
    -0.50
    POSITIVE LOGITS
     scandal
    1.16
     scandals
    1.11
     Scandal
    1.04
     scandalous
    0.77
     Scand
    0.66
     involving
    0.64
    Lmfao
    0.64
    naphthal
    0.58
     Alcalde
    0.58
     Compañ
    0.58
    Activations Density 0.094%

    No Known Activations