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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 11995
    Prev
    Next
    INDEX
    Explanations

    discussions around interviews and personal insights related to experiences and inspirations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases where the writer/speaker refers to themselves conducting or reporting an interview or conversation (first‑person reporter/“I” voice).

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    })));
    -0.77
    }))
    
    -0.74
     Allociné
    -0.68
    omock
    -0.62
    ientôt
    -0.62
     Alembic
    -0.61
    lioz
    -0.61
    )++;
    -0.60
    withIdentifier
    -0.59
    ताब
    -0.59
    POSITIVE LOGITS
     interview
    1.05
    interview
    0.93
    Interview
    0.93
     Interview
    0.87
     interviews
    0.87
     interviewed
    0.84
     interviewees
    0.81
     INTERVIEW
    0.76
     entrevista
    0.76
    インタビュー
    0.71
    Activations Density 0.230%

    No Known Activations