© 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. 14531
    Prev
    Next
    INDEX
    Explanations

    references to categories or classifications of specific items

    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
    1177
    +0.15
    0.5%
    184
    +0.13
    0.4%
    2006
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    802
    +0.15
    0.06
    1919
    +0.13
    0.05
    908
    +0.09
    0.02
    Negative Logits
    脚注の使い方
    -0.70
    HomeAsUpEnabled
    -0.69
     CreateTagHelper
    -0.64
    esModule
    -0.60
    nocache
    -0.60
    ‌.
    -0.57
    دانشنامهٔ
    -0.57
    SharedDtor
    -0.57
    reportWebVitals
    -0.57
     autorytatywna
    -0.56
    POSITIVE LOGITS
     purcha
    1.46
     guarante
    1.44
     snoopy
    1.44
     apprehen
    1.43
     affor
    1.42
     disagre
    1.41
     reluct
    1.39
     strick
    1.39
     desir
    1.39
     greate
    1.38
    Activations Density 0.361%

    No Known Activations