Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14590
    Prev
    Next
    INDEX
    Explanations

    instances of the word "end" and related concepts that indicate conclusion or termination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.51
    mstyle
    -0.49
    googleapis
    -0.49
    alnız
    -0.46
     citoy
    -0.45
    trane
    -0.44
    lccn
    -0.42
    GrantedAuthority
    -0.42
     Agrico
    -0.42
     VIAF
    -0.41
    POSITIVE LOGITS
     end
    1.12
     End
    1.09
    End
    1.08
    setEnd
    1.07
    getEnd
    1.02
    end
    1.00
     END
    1.00
     Endgame
    0.94
     ends
    0.90
    END
    0.89
    Activations Density 0.139%

    No Known Activations