© 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. 14254
    Prev
    Next
    INDEX
    Explanations

    terms or phrases related to spatial location or distribution

    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
    406
    +0.12
    0.4%
    492
    +0.12
    0.4%
    297
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    492
    +0.12
    0.05
    406
    +0.12
    0.03
    1404
    +0.11
    0.04
    Negative Logits
     --;
    -0.50
    BeforeMethod
    -0.49
    Perú
    -0.48
     MwSt
    -0.47
     NUKAT
    -0.47
    Ofic
    -0.47
    ByUrl
    -0.47
    Nguyên
    -0.46
    memoized
    -0.46
    EventQueue
    -0.46
    POSITIVE LOGITS
     ACROSS
    1.11
    across
    1.06
     Across
    1.04
     across
    1.02
    Across
    0.97
     broder
    0.87
     matel
    0.84
     tranf
    0.81
     tremb
    0.81
     chande
    0.80
    Activations Density 0.070%

    No Known Activations