© 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. 3515
    Prev
    Next
    INDEX
    Explanations

    conditions related to confinement or deprivation

    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
    50
    +0.19
    0.6%
    856
    +0.10
    0.3%
    1108
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    612
    +0.19
    -0.00
    50
    +0.10
    0.06
    1695
    +0.10
    0.05
    Negative Logits
    （
    -0.45
    、
    -0.44
     Manchuria
    -0.44
    ，
    -0.43
     trod
    -0.43
     smacked
    -0.43
     crept
    -0.42
    ,
    -0.42
     strangled
    -0.42
     swoop
    -0.41
    POSITIVE LOGITS
    Glej
    0.90
     ananas
    0.82
     GRATU
    0.78
     habile
    0.74
    Bardzo
    0.74
    Zunanje
    0.74
     cabrio
    0.73
     ridu
    0.73
     bont
    0.72
     XIAOMI
    0.71
    Activations Density 0.591%

    No Known Activations