© 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. 13068
    Prev
    Next
    INDEX
    Explanations

    descriptions of violent incidents and construction projects

    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
    906
    +0.14
    0.4%
    1150
    +0.12
    0.4%
    845
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    964
    +0.14
    0.04
    790
    +0.12
    0.03
    227
    +0.12
    0.05
    Negative Logits
    principalColumn
    -0.73
    Hozzáférés
    -0.70
     Käse
    -0.66
    ErrorListener
    -0.65
     AspNetCore
    -0.64
     ISNI
    -0.64
    RegressionTest
    -0.64
    Abbiamo
    -0.63
    abestanden
    -0.62
     Zwiebel
    -0.62
    POSITIVE LOGITS
     shenan
    1.33
     intersper
    1.32
     encomp
    1.32
     reluct
    1.29
     philanth
    1.25
     maneu
    1.24
     resear
    1.22
     disagre
    1.21
     Gorb
    1.18
     Juf
    1.17
    Activations Density 0.399%

    No Known Activations