© 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. 14502
    Prev
    Next
    INDEX
    Explanations

    information related to news events and protests

    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
    381
    +0.11
    0.3%
    1056
    +0.10
    0.3%
    468
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.11
    0.09
    752
    +0.10
    0.05
    1056
    +0.10
    0.07
    Negative Logits
    WEBPACK
    -0.54
     OMIT
    -0.54
    breo
    -0.52
    ykjav
    -0.52
    ionais
    -0.51
    altor
    -0.51
    >?
    -0.51
    Làm
    -0.50
     Himo
    -0.49
     thereof
    -0.49
    POSITIVE LOGITS
     intersper
    1.06
     apprehen
    1.04
     maneu
    1.02
     reluct
    1.01
     shenan
    1.01
     disagre
    0.99
     fortn
    0.98
     reconno
    0.98
     impra
    0.96
     encomp
    0.94
    Activations Density 0.743%

    No Known Activations