© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 442
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences starting with the word "Say"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1618
    +0.09
    0.2%
    1604
    +0.07
    0.2%
    506
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.09
    0.03
    1343
    +0.07
    0.03
    542
    +0.07
    0.02
    Negative Logits
     rolle
    -0.59
     solidar
    -0.57
    CodeAttribute
    -0.55
     fisk
    -0.55
     kroner
    -0.54
     identif
    -0.53
    llbracket
    -0.52
     kasa
    -0.51
     bevor
    -0.51
     fide
    -0.51
    POSITIVE LOGITS
     Say
    2.22
    Say
    1.95
     murano
    1.40
     véhic
    1.37
    SAY
    1.33
     lamborghini
    1.21
     rafra
    1.19
     Février
    1.12
     télécharge
    1.11
     ibiza
    1.11
    Activations Density 0.245%

    No Known Activations