© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7793
    Prev
    Next
    INDEX
    Explanations

    descriptions of geological exploration activities and related mineral deposits

    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
    50
    +0.17
    0.5%
    946
    +0.13
    0.4%
    939
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.17
    0.08
    939
    +0.13
    0.08
    194
    +0.12
    0.02
    Negative Logits
     gela
    -0.73
     Wikisource
    -0.59
     nabi
    -0.55
    ">:
    -0.53
    麒麟
    -0.53
     typelib
    -0.53
     LUMP
    -0.53
     psicologia
    -0.53
    AddTagHelper
    -0.53
    🎰
    -0.52
    POSITIVE LOGITS
     sovere
    1.18
     depic
    1.17
     unwarran
    1.16
     unlaw
    1.13
     encomp
    1.11
     perfon
    1.10
     liberality
    1.09
     disagre
    1.08
     ftu
    1.07
     Shakspeare
    1.06
    Activations Density 1.036%

    No Known Activations